1.1 Structured Data
- Software classifies data by type.
- Numeric (continuous or discrete)
- Categorical (binary, ordinal, neither)
- Rectangular data = typical frame of reference for data science.
- Called a
data.framein R - Rows are records (aka observations, cases, instances)
- Columns are features (aka variables, attributes, predictors in some cases)
- Lots of synonyms in stats and data science for same things.
- Called a